关于图像分割算法的优化仿真研究

An Improved Image Segmentation Algorithm Based on Otsu Method

Otsu图像分割法是常用的图像阈值分割方法,其最佳阈值选取直接影响到图像分割的质量。传统的最佳阈值的寻找采用穷尽式搜索方法,计算复杂度大,耗时较多,分割的精度低,易产生图像误分割。为了提高图像分割准确性,提出一种遗传算法与O tsu相结合的图像分割方法。新方法将图像分割问题看作为一个全局数值优化问题,将图像灰度信息转换成遗传算法的种群,每个个体代表一个可行的阈值向量,以灰度图像的灰度最大类间方差作为适应度值,通过选择、交叉和变异等遗传操作获得图像最佳分割阈值,以获得的最佳阈值对图像进行分割。用实例对新方法进行验证实验,结果表明,相对于传统Ostu图像分割算法,改进的O tsu分割方法提高了图像分割准确性,运算量减少,加快了分割速度,非常适应于图像实时处理。

In most ostu image segmentation algorithms,the optimum threshold choice is the key to image segmentation.Traditional ostu threshold is selected by exhaustive search algorithmon,which it is of high time cost,low efficiency,and easy to produce error.In order to improve the efficiency and the accuracy of segmentation image segmentation,this paper puts forward an improved ostu algorithm based on a genetic algorithm.The method takes image segmentation problem as a global numerical optimization problem,converts image grey information into the population of genetic algorithm,with each individual species representing a feasible threshold,the maximum gray variance between clusters as the fitness value.Through the genetic operations of choice,crossover and mutation,optimal threshold is obtained to carry out the optimal threshold segmentation.The experimental results show that compared with the traditional algorithm,this method improves the calculation accuracy of image segmentation,and accelerates the segmentation speed,and is very suitable for real-time image processing.